MPSCNNConvolutionDescriptor (moe.platform.ios API)

java.lang.Object
- org.moe.natj.general.NativeObject
- - org.moe.natj.objc.ObjCObject
  - - apple.NSObject
    - - apple.metalperformanceshaders.MPSCNNConvolutionDescriptor

All Implemented Interfaces:

NSCoding, NSCopying, NSSecureCoding, NSObject

Direct Known Subclasses:

MPSCNNDepthWiseConvolutionDescriptor, MPSCNNSubPixelConvolutionDescriptor
```
public class MPSCNNConvolutionDescriptor
extends NSObject
implements NSSecureCoding, NSCopying
```
MPSCNNConvolutionDescriptor [@dependency] This depends on Metal.framework
The MPSCNNConvolutionDescriptor specifies a convolution descriptor

Nested Class Summary
- Nested classes/interfaces inherited from class apple.NSObject
  NSObject.Function_instanceMethodForSelector_ret, NSObject.Function_methodForSelector_ret

Constructor Summary

Constructors
Modifier Constructor and Description

protected MPSCNNConvolutionDescriptor(org.moe.natj.general.Pointer peer)

Constructors
Modifier	Constructor and Description
`protected`	`MPSCNNConvolutionDescriptor(org.moe.natj.general.Pointer peer)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`boolean`	`_supportsSecureCoding()` This property must return YES on all classes that allow secure coding.
`static boolean`	`accessInstanceVariablesDirectly()`
`static MPSCNNConvolutionDescriptor`	`alloc()`
`static MPSCNNConvolutionDescriptor`	`allocWithZone(org.moe.natj.general.ptr.VoidPtr zone)`
`static boolean`	`automaticallyNotifiesObserversForKey(java.lang.String key)`
`static void`	`cancelPreviousPerformRequestsWithTarget(java.lang.Object aTarget)`
`static void`	`cancelPreviousPerformRequestsWithTargetSelectorObject(java.lang.Object aTarget, org.moe.natj.objc.SEL aSelector, java.lang.Object anArgument)`
`static NSArray<java.lang.String>`	`classFallbacksForKeyedArchiver()`
`static org.moe.natj.objc.Class`	`classForKeyedUnarchiver()`
`static MPSCNNConvolutionDescriptor`	`cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannels(long kernelWidth, long kernelHeight, long inputFeatureChannels, long outputFeatureChannels)` Creates a convolution descriptor.
`static MPSCNNConvolutionDescriptor`	`cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannelsNeuronFilter(long kernelWidth, long kernelHeight, long inputFeatureChannels, long outputFeatureChannels, MPSCNNNeuron neuronFilter)` This method is deprecated.
`java.lang.Object`	`copyWithZone(org.moe.natj.general.ptr.VoidPtr zone)`
`static java.lang.String`	`debugDescription_static()`
`static java.lang.String`	`description_static()`
`long`	`dilationRateX()` [@property] dilationRateX
`long`	`dilationRateY()` [@property] dilationRateY
`void`	`encodeWithCoder(NSCoder aCoder)`
`MPSNNNeuronDescriptor`	`fusedNeuronDescriptor()` [@property] fusedNeuronDescriptor
`long`	`groups()` [@property] groups
`static long`	`hash_static()`
`MPSCNNConvolutionDescriptor`	`init()`
`MPSCNNConvolutionDescriptor`	`initWithCoder(NSCoder aDecoder)` NS_DESIGNATED_INITIALIZER
`long`	`inputFeatureChannels()` [@property] inputFeatureChannels
`static NSObject.Function_instanceMethodForSelector_ret`	`instanceMethodForSelector(org.moe.natj.objc.SEL aSelector)`
`static NSMethodSignature`	`instanceMethodSignatureForSelector(org.moe.natj.objc.SEL aSelector)`
`static boolean`	`instancesRespondToSelector(org.moe.natj.objc.SEL aSelector)`
`static boolean`	`isSubclassOfClass(org.moe.natj.objc.Class aClass)`
`long`	`kernelHeight()` [@property] kernelHeight
`long`	`kernelWidth()` [@property] kernelWidth
`static NSSet<java.lang.String>`	`keyPathsForValuesAffectingValueForKey(java.lang.String key)`
`MPSCNNNeuron`	`neuron()` [@property] neuron
`float`	`neuronParameterA()` Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
`float`	`neuronParameterB()` Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
`int`	`neuronType()` Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
`static MPSCNNConvolutionDescriptor`	`new_objc()`
`long`	`outputFeatureChannels()` [@property] outputFeatureChannels
`static boolean`	`resolveClassMethod(org.moe.natj.objc.SEL sel)`
`static boolean`	`resolveInstanceMethod(org.moe.natj.objc.SEL sel)`
`void`	`setBatchNormalizationParametersForInferenceWithMeanVarianceGammaBetaEpsilon(org.moe.natj.general.ptr.ConstFloatPtr mean, org.moe.natj.general.ptr.ConstFloatPtr variance, org.moe.natj.general.ptr.ConstFloatPtr gamma, org.moe.natj.general.ptr.ConstFloatPtr beta, float epsilon)` Adds batch normalization for inference, it copies all the float arrays provided, expecting outputFeatureChannels elements in each.
`void`	`setDilationRateX(long value)` [@property] dilationRateX
`void`	`setDilationRateY(long value)` [@property] dilationRateY
`void`	`setFusedNeuronDescriptor(MPSNNNeuronDescriptor value)` [@property] fusedNeuronDescriptor
`void`	`setGroups(long value)` [@property] groups
`void`	`setInputFeatureChannels(long value)` [@property] inputFeatureChannels
`void`	`setKernelHeight(long value)` [@property] kernelHeight
`void`	`setKernelWidth(long value)` [@property] kernelWidth
`void`	`setNeuron(MPSCNNNeuron value)` [@property] neuron
`void`	`setNeuronToPReLUWithParametersA(NSData A)` Add per-channel neuron parameters A for PReLu neuron activation functions.
`void`	`setNeuronTypeParameterAParameterB(int neuronType, float parameterA, float parameterB)` Adds a neuron activation function to convolution descriptor.
`void`	`setOutputFeatureChannels(long value)` [@property] outputFeatureChannels
`void`	`setStrideInPixelsX(long value)` [@property] strideInPixelsX
`void`	`setStrideInPixelsY(long value)` [@property] strideInPixelsY
`static void`	`setVersion_static(long aVersion)`
`long`	`strideInPixelsX()` [@property] strideInPixelsX
`long`	`strideInPixelsY()` [@property] strideInPixelsY
`static org.moe.natj.objc.Class`	`superclass_static()`
`static boolean`	`supportsSecureCoding()`
`static long`	`version_static()`

Methods inherited from class apple.NSObject
accessibilityActivate, accessibilityActivationPoint, accessibilityAssistiveTechnologyFocusedIdentifiers, accessibilityAttributedHint, accessibilityAttributedLabel, accessibilityAttributedUserInputLabels, accessibilityAttributedValue, accessibilityContainerType, accessibilityCustomActions, accessibilityCustomRotors, accessibilityDecrement, accessibilityDragSourceDescriptors, accessibilityDropPointDescriptors, accessibilityElementAtIndex, accessibilityElementCount, accessibilityElementDidBecomeFocused, accessibilityElementDidLoseFocus, accessibilityElementIsFocused, accessibilityElements, accessibilityElementsHidden, accessibilityFrame, accessibilityHint, accessibilityIncrement, accessibilityLabel, accessibilityLanguage, accessibilityNavigationStyle, accessibilityPath, accessibilityPerformEscape, accessibilityPerformMagicTap, accessibilityRespondsToUserInteraction, accessibilityScroll, accessibilityTextualContext, accessibilityTraits, accessibilityUserInputLabels, accessibilityValue, accessibilityViewIsModal, addObserverForKeyPathOptionsContext, attemptRecoveryFromErrorOptionIndex, attemptRecoveryFromErrorOptionIndexDelegateDidRecoverSelectorContextInfo, autoContentAccessingProxy, awakeAfterUsingCoder, awakeFromNib, class_objc, classForCoder, classForKeyedArchiver, copy, dealloc, debugDescription, description, dictionaryWithValuesForKeys, didChangeValueForKey, didChangeValueForKeyWithSetMutationUsingObjects, didChangeValuesAtIndexesForKey, doesNotRecognizeSelector, fileManagerShouldProceedAfterError, fileManagerWillProcessPath, finalize_objc, forwardingTargetForSelector, forwardInvocation, hash, indexOfAccessibilityElement, isAccessibilityElement, isEqual, isKindOfClass, isMemberOfClass, isProxy, methodForSelector, methodSignatureForSelector, mutableArrayValueForKey, mutableArrayValueForKeyPath, mutableCopy, mutableOrderedSetValueForKey, mutableOrderedSetValueForKeyPath, mutableSetValueForKey, mutableSetValueForKeyPath, observationInfo, observeValueForKeyPathOfObjectChangeContext, performSelector, performSelectorInBackgroundWithObject, performSelectorOnMainThreadWithObjectWaitUntilDone, performSelectorOnMainThreadWithObjectWaitUntilDoneModes, performSelectorOnThreadWithObjectWaitUntilDone, performSelectorOnThreadWithObjectWaitUntilDoneModes, performSelectorWithObject, performSelectorWithObjectAfterDelay, performSelectorWithObjectAfterDelayInModes, performSelectorWithObjectWithObject, prepareForInterfaceBuilder, provideImageDataBytesPerRowOrigin_Size_UserInfo, removeObserverForKeyPath, removeObserverForKeyPathContext, replacementObjectForCoder, replacementObjectForKeyedArchiver, respondsToSelector, self, setAccessibilityActivationPoint, setAccessibilityAttributedHint, setAccessibilityAttributedLabel, setAccessibilityAttributedUserInputLabels, setAccessibilityAttributedValue, setAccessibilityContainerType, setAccessibilityCustomActions, setAccessibilityCustomRotors, setAccessibilityDragSourceDescriptors, setAccessibilityDropPointDescriptors, setAccessibilityElements, setAccessibilityElementsHidden, setAccessibilityFrame, setAccessibilityHint, setAccessibilityLabel, setAccessibilityLanguage, setAccessibilityNavigationStyle, setAccessibilityPath, setAccessibilityRespondsToUserInteraction, setAccessibilityTextualContext, setAccessibilityTraits, setAccessibilityUserInputLabels, setAccessibilityValue, setAccessibilityViewIsModal, setIsAccessibilityElement, setNilValueForKey, setObservationInfo, setShouldGroupAccessibilityChildren, setValueForKey, setValueForKeyPath, setValueForUndefinedKey, setValuesForKeysWithDictionary, shouldGroupAccessibilityChildren, superclass, validateValueForKeyError, validateValueForKeyPathError, valueForKey, valueForKeyPath, valueForUndefinedKey, willChangeValueForKey, willChangeValueForKeyWithSetMutationUsingObjects, willChangeValuesAtIndexesForKey

Methods inherited from class org.moe.natj.objc.ObjCObject
equals, toString

Methods inherited from class org.moe.natj.general.NativeObject
finalize, getPeer, getPeerPointer

Methods inherited from class java.lang.Object
clone, getClass, hashCode, notify, notifyAll, wait, wait, wait

- Constructor Detail
  - MPSCNNConvolutionDescriptor
```
protected MPSCNNConvolutionDescriptor(org.moe.natj.general.Pointer peer)
```
- Method Detail
  - accessInstanceVariablesDirectly
```
public static boolean accessInstanceVariablesDirectly()
```
  - alloc
```
public static MPSCNNConvolutionDescriptor alloc()
```
  - allocWithZone
```
public static MPSCNNConvolutionDescriptor allocWithZone(org.moe.natj.general.ptr.VoidPtr zone)
```
  - automaticallyNotifiesObserversForKey
```
public static boolean automaticallyNotifiesObserversForKey(java.lang.String key)
```
  - cancelPreviousPerformRequestsWithTarget
```
public static void cancelPreviousPerformRequestsWithTarget(java.lang.Object aTarget)
```
  - cancelPreviousPerformRequestsWithTargetSelectorObject
```
public static void cancelPreviousPerformRequestsWithTargetSelectorObject(java.lang.Object aTarget,
                                                                         org.moe.natj.objc.SEL aSelector,
                                                                         java.lang.Object anArgument)
```
  - classFallbacksForKeyedArchiver
```
public static NSArray<java.lang.String> classFallbacksForKeyedArchiver()
```
  - classForKeyedUnarchiver
```
public static org.moe.natj.objc.Class classForKeyedUnarchiver()
```
  - cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannelsNeuronFilter
```
public static MPSCNNConvolutionDescriptor cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannelsNeuronFilter(long kernelWidth,
                                                                                                                                                   long kernelHeight,
                                                                                                                                                   long inputFeatureChannels,
                                                                                                                                                   long outputFeatureChannels,
                                                                                                                                                   MPSCNNNeuron neuronFilter)
```
    This method is deprecated. Please use neuronType, neuronParameterA and neuronParameterB properites to fuse neuron with convolution.
    
    Parameters:
    
    kernelWidth - The width of the filter window. Must be > 0. Large values will take a long time.
    
    kernelHeight - The height of the filter window. Must be > 0. Large values will take a long time.
    
    inputFeatureChannels - The number of feature channels in the input image. Must be >= 1.
    
    outputFeatureChannels - The number of feature channels in the output image. Must be >= 1.
    
    neuronFilter - An optional neuron filter that can be applied to the output of convolution.
    
    Returns:
    
    A valid MPSCNNConvolutionDescriptor object or nil, if failure.
  - debugDescription_static
```
public static java.lang.String debugDescription_static()
```
  - description_static
```
public static java.lang.String description_static()
```
  - hash_static
```
public static long hash_static()
```
  - instanceMethodForSelector
```
public static NSObject.Function_instanceMethodForSelector_ret instanceMethodForSelector(org.moe.natj.objc.SEL aSelector)
```
  - instanceMethodSignatureForSelector
```
public static NSMethodSignature instanceMethodSignatureForSelector(org.moe.natj.objc.SEL aSelector)
```
  - instancesRespondToSelector
```
public static boolean instancesRespondToSelector(org.moe.natj.objc.SEL aSelector)
```
  - isSubclassOfClass
```
public static boolean isSubclassOfClass(org.moe.natj.objc.Class aClass)
```
  - keyPathsForValuesAffectingValueForKey
```
public static NSSet<java.lang.String> keyPathsForValuesAffectingValueForKey(java.lang.String key)
```
  - new_objc
```
public static MPSCNNConvolutionDescriptor new_objc()
```
  - resolveClassMethod
```
public static boolean resolveClassMethod(org.moe.natj.objc.SEL sel)
```
  - resolveInstanceMethod
```
public static boolean resolveInstanceMethod(org.moe.natj.objc.SEL sel)
```
  - setVersion_static
```
public static void setVersion_static(long aVersion)
```
  - superclass_static
```
public static org.moe.natj.objc.Class superclass_static()
```
  - version_static
```
public static long version_static()
```
  - copyWithZone
```
public java.lang.Object copyWithZone(org.moe.natj.general.ptr.VoidPtr zone)
```
    Specified by:
    
    copyWithZone in interface NSCopying
  - groups
```
public long groups()
```
    [@property] groups
    Number of groups input and output channels are divided into. The default value is 1. Groups lets you reduce the parameterization. If groups is set to n, input is divided into n groups with inputFeatureChannels/n channels in each group. Similarly output is divided into n groups with outputFeatureChannels/n channels in each group. ith group in input is only connected to ith group in output so number of weights (parameters) needed is reduced by factor of n. Both inputFeatureChannels and outputFeatureChannels must be divisible by n and number of channels in each group must be multiple of 4.
  - init
```
public MPSCNNConvolutionDescriptor init()
```
    Overrides:
    
    init in class NSObject
  - inputFeatureChannels
```
public long inputFeatureChannels()
```
    [@property] inputFeatureChannels
    The number of feature channels per pixel in the input image.
  - kernelHeight
```
public long kernelHeight()
```
    [@property] kernelHeight
    The height of the filter window. The default value is 3. Any positive non-zero value is valid, including even values. The position of the top edge of the filter window is given by offset.y - (kernelHeight>>1)
  - kernelWidth
```
public long kernelWidth()
```
    [@property] kernelWidth
    The width of the filter window. The default value is 3. Any positive non-zero value is valid, including even values. The position of the left edge of the filter window is given by offset.x - (kernelWidth>>1)
  - neuron
```
public MPSCNNNeuron neuron()
```
    [@property] neuron
    MPSCNNNeuron filter to be applied as part of convolution. This is applied after BatchNormalization in the end. Default is nil. This is deprecated. You dont need to create MPSCNNNeuron object to fuse with convolution. Use neuron properties in this descriptor.
  - outputFeatureChannels
```
public long outputFeatureChannels()
```
    [@property] outputFeatureChannels
    The number of feature channels per pixel in the output image.
  - setGroups
```
public void setGroups(long value)
```
    [@property] groups
    Number of groups input and output channels are divided into. The default value is 1. Groups lets you reduce the parameterization. If groups is set to n, input is divided into n groups with inputFeatureChannels/n channels in each group. Similarly output is divided into n groups with outputFeatureChannels/n channels in each group. ith group in input is only connected to ith group in output so number of weights (parameters) needed is reduced by factor of n. Both inputFeatureChannels and outputFeatureChannels must be divisible by n and number of channels in each group must be multiple of 4.
  - setInputFeatureChannels
```
public void setInputFeatureChannels(long value)
```
    [@property] inputFeatureChannels
    The number of feature channels per pixel in the input image.
  - setKernelHeight
```
public void setKernelHeight(long value)
```
    [@property] kernelHeight
    The height of the filter window. The default value is 3. Any positive non-zero value is valid, including even values. The position of the top edge of the filter window is given by offset.y - (kernelHeight>>1)
  - setKernelWidth
```
public void setKernelWidth(long value)
```
    [@property] kernelWidth
    The width of the filter window. The default value is 3. Any positive non-zero value is valid, including even values. The position of the left edge of the filter window is given by offset.x - (kernelWidth>>1)
  - setNeuron
```
public void setNeuron(MPSCNNNeuron value)
```
    [@property] neuron
    MPSCNNNeuron filter to be applied as part of convolution. This is applied after BatchNormalization in the end. Default is nil. This is deprecated. You dont need to create MPSCNNNeuron object to fuse with convolution. Use neuron properties in this descriptor.
  - setOutputFeatureChannels
```
public void setOutputFeatureChannels(long value)
```
    [@property] outputFeatureChannels
    The number of feature channels per pixel in the output image.
  - setStrideInPixelsX
```
public void setStrideInPixelsX(long value)
```
    [@property] strideInPixelsX
    The output stride (downsampling factor) in the x dimension. The default value is 1.
  - setStrideInPixelsY
```
public void setStrideInPixelsY(long value)
```
    [@property] strideInPixelsY
    The output stride (downsampling factor) in the y dimension. The default value is 1.
  - strideInPixelsX
```
public long strideInPixelsX()
```
    [@property] strideInPixelsX
    The output stride (downsampling factor) in the x dimension. The default value is 1.
  - strideInPixelsY
```
public long strideInPixelsY()
```
    [@property] strideInPixelsY
    The output stride (downsampling factor) in the y dimension. The default value is 1.
  - cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannels
```
public static MPSCNNConvolutionDescriptor cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannels(long kernelWidth,
                                                                                                                                       long kernelHeight,
                                                                                                                                       long inputFeatureChannels,
                                                                                                                                       long outputFeatureChannels)
```
    Creates a convolution descriptor.
    
    Parameters:
    
    kernelWidth - The width of the filter window. Must be > 0. Large values will take a long time.
    
    kernelHeight - The height of the filter window. Must be > 0. Large values will take a long time.
    
    inputFeatureChannels - The number of feature channels in the input image. Must be >= 1.
    
    outputFeatureChannels - The number of feature channels in the output image. Must be >= 1.
    
    Returns:
    
    A valid MPSCNNConvolutionDescriptor object or nil, if failure.
  - dilationRateX
```
public long dilationRateX()
```
    [@property] dilationRateX
    dilationRateX property can be used to implement dilated convolution as described in https://arxiv.org/pdf/1511.07122v3.pdf to aggregate global information in dense prediction problems. Default value is 1. When set to value > 1, original kernel width, kW is dilated to
    kW_Dilated = (kW-1)*dilationRateX + 1
    by inserting d-1 zeros between consecutive entries in each row of the original kernel. The kernel is centered based on kW_Dilated.
  - dilationRateY
```
public long dilationRateY()
```
    [@property] dilationRateY
    dilationRateY property can be used to implement dilated convolution as described in https://arxiv.org/pdf/1511.07122v3.pdf to aggregate global information in dense prediction problems. Default value is 1. When set to value > 1, original kernel height, kH is dilated to
    kH_Dilated = (kH-1)*dilationRateY + 1
    by inserting d-1 rows of zeros between consecutive row of the original kernel. The kernel is centered based on kH_Dilated.
  - encodeWithCoder
```
public void encodeWithCoder(NSCoder aCoder)
```
    Specified by:
    
    encodeWithCoder in interface NSCoding
  - initWithCoder
```
public MPSCNNConvolutionDescriptor initWithCoder(NSCoder aDecoder)
```
    Description copied from interface: NSCoding
    
    NS_DESIGNATED_INITIALIZER
    
    Specified by:
    
    initWithCoder in interface NSCoding
  - neuronParameterA
```
public float neuronParameterA()
```
    Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
  - neuronParameterB
```
public float neuronParameterB()
```
    Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
  - neuronType
```
public int neuronType()
```
    Getter funtion for neuronType set using setNeuronType:parameterA:parameterB method
  - setBatchNormalizationParametersForInferenceWithMeanVarianceGammaBetaEpsilon
```
public void setBatchNormalizationParametersForInferenceWithMeanVarianceGammaBetaEpsilon(org.moe.natj.general.ptr.ConstFloatPtr mean,
                                                                                        org.moe.natj.general.ptr.ConstFloatPtr variance,
                                                                                        org.moe.natj.general.ptr.ConstFloatPtr gamma,
                                                                                        org.moe.natj.general.ptr.ConstFloatPtr beta,
                                                                                        float epsilon)
```
    Adds batch normalization for inference, it copies all the float arrays provided, expecting outputFeatureChannels elements in each.
    This method will be used to pass in batch normalization parameters to the convolution during the init call. For inference we modify weights and bias going in convolution or Fully Connected layer to combine and optimize the layers.
    
    w: weights for a corresponding output feature channel b: bias for a corresponding output feature channel W: batch normalized weights for a corresponding output feature channel B: batch normalized bias for a corresponding output feature channel
    
    I = gamma / sqrt(variance + epsilon), J = beta - ( I * mean )
    W = w * I B = b * I + J
    Every convolution has (OutputFeatureChannel * kernelWidth * kernelHeight * InputFeatureChannel) weights
    I, J are calculated, for every output feature channel separately to get the corresponding weights and bias Thus, I, J are calculated and then used for every (kernelWidth * kernelHeight * InputFeatureChannel) weights, and this is done OutputFeatureChannel number of times for each output channel.
    thus, internally, batch normalized weights are computed as:
    W[no][i][j][ni] = w[no][i][j][ni] * I[no]
    no: index into outputFeatureChannel i : index into kernel Height j : index into kernel Width ni: index into inputFeatureChannel
    One usually doesn't see a bias term and batch normalization together as batch normalization potentially cancels out the bias term after training, but in MPS if the user provides it, batch normalization will use the above formula to incorporate it, if user does not have bias terms then put a float array of zeroes in the convolution init for bias terms of each output feature channel.
    
    this comes from: https://arxiv.org/pdf/1502.03167v3.pdf
    Note: in certain cases the batch normalization parameters will be cached by the MPSNNGraph or the MPSCNNConvolution. If the batch normalization parameters change after either is made, behavior is undefined.
    
    Parameters:
    
    mean - Pointer to an array of floats of mean for each output feature channel
    
    variance - Pointer to an array of floats of variance for each output feature channel
    
    gamma - Pointer to an array of floats of gamma for each output feature channel
    
    beta - Pointer to an array of floats of beta for each output feature channel
    
    epsilon - A small float value used to have numerical stability in the code
  - setDilationRateX
```
public void setDilationRateX(long value)
```
    [@property] dilationRateX
    dilationRateX property can be used to implement dilated convolution as described in https://arxiv.org/pdf/1511.07122v3.pdf to aggregate global information in dense prediction problems. Default value is 1. When set to value > 1, original kernel width, kW is dilated to
    kW_Dilated = (kW-1)*dilationRateX + 1
    by inserting d-1 zeros between consecutive entries in each row of the original kernel. The kernel is centered based on kW_Dilated.
  - setDilationRateY
```
public void setDilationRateY(long value)
```
    [@property] dilationRateY
    dilationRateY property can be used to implement dilated convolution as described in https://arxiv.org/pdf/1511.07122v3.pdf to aggregate global information in dense prediction problems. Default value is 1. When set to value > 1, original kernel height, kH is dilated to
    kH_Dilated = (kH-1)*dilationRateY + 1
    by inserting d-1 rows of zeros between consecutive row of the original kernel. The kernel is centered based on kH_Dilated.
  - setNeuronToPReLUWithParametersA
```
public void setNeuronToPReLUWithParametersA(NSData A)
```
    Add per-channel neuron parameters A for PReLu neuron activation functions.
    This method sets the neuron to PReLU, zeros parameters A and B and sets the per-channel neuron parameters A to an array containing a unique value of A for each output feature channel.
    If the neuron function is f(v,a,b), it will apply
    OutputImage(x,y,i) = f( ConvolutionResult(x,y,i), A[i], B[i] ) where i in [0,outputFeatureChannels-1]
    See https://arxiv.org/pdf/1502.01852.pdf for details.
    All other neuron types, where parameter A and parameter B are shared across channels must be set using -setNeuronOfType:parameterA:parameterB:
    If batch normalization parameters are set, batch normalization will occur before neuron application i.e. output of convolution is first batch normalized followed by neuron activation. This function automatically sets neuronType to MPSCNNNeuronTypePReLU.
    Note: in certain cases the neuron descriptor will be cached by the MPSNNGraph or the MPSCNNConvolution. If the neuron type changes after either is made, behavior is undefined.
    
    Parameters:
    
    A - An array containing per-channel float values for neuron parameter A. Number of entries must be equal to outputFeatureChannels.
  - setNeuronTypeParameterAParameterB
```
public void setNeuronTypeParameterAParameterB(int neuronType,
                                              float parameterA,
                                              float parameterB)
```
    Adds a neuron activation function to convolution descriptor.
    This mathod can be used to add a neuron activation funtion of given type with associated scalar parameters A and B that are shared across all output channels. Neuron activation fucntion is applied to output of convolution. This is a per-pixel operation that is fused with convolution kernel itself for best performance. Note that this method can only be used to fuse neuron of kind for which parameters A and B are shared across all channels of convoution output. It is an error to call this method for neuron activation functions like MPSCNNNeuronTypePReLU, which require per-channel parameter values. For those kind of neuron activation functions, use appropriate setter functions.
    Note: in certain cases, the neuron descriptor will be cached by the MPSNNGraph or the MPSCNNConvolution. If the neuron type changes after either is made, behavior is undefined.
    
    Parameters:
    
    neuronType - type of neuron activation function. For full list see MPSCNNNeuronType.h
    
    parameterA - parameterA of neuron activation that is shared across all channels of convolution output.
    
    parameterB - parameterB of neuron activation that is shared across all channels of convolution output.
  - supportsSecureCoding
```
public static boolean supportsSecureCoding()
```
  - _supportsSecureCoding
```
public boolean _supportsSecureCoding()
```
    Description copied from interface: NSSecureCoding
    
    This property must return YES on all classes that allow secure coding. Subclasses of classes that adopt NSSecureCoding and override initWithCoder: must also override this method and return YES. The Secure Coding Guide should be consulted when writing methods that decode data.
    
    Specified by:
    
    _supportsSecureCoding in interface NSSecureCoding
  - fusedNeuronDescriptor
```
public MPSNNNeuronDescriptor fusedNeuronDescriptor()
```
    [@property] fusedNeuronDescriptor
    This mathod can be used to add a neuron activation funtion of given type with associated scalar parameters A and B that are shared across all output channels. Neuron activation fucntion is applied to output of convolution. This is a per-pixel operation that is fused with convolution kernel itself for best performance. Note that this method can only be used to fuse neuron of kind for which parameters A and B are shared across all channels of convoution output. It is an error to call this method for neuron activation functions like MPSCNNNeuronTypePReLU, which require per-channel parameter values. For those kind of neuron activation functions, use appropriate setter functions. Default is descriptor with neuronType MPSCNNNeuronTypeNone.
    Note: in certain cases the neuron descriptor will be cached by the MPSNNGraph or the MPSCNNConvolution. If the neuron type changes after either is made, behavior is undefined.
  - setFusedNeuronDescriptor
```
public void setFusedNeuronDescriptor(MPSNNNeuronDescriptor value)
```
    [@property] fusedNeuronDescriptor
    This mathod can be used to add a neuron activation funtion of given type with associated scalar parameters A and B that are shared across all output channels. Neuron activation fucntion is applied to output of convolution. This is a per-pixel operation that is fused with convolution kernel itself for best performance. Note that this method can only be used to fuse neuron of kind for which parameters A and B are shared across all channels of convoution output. It is an error to call this method for neuron activation functions like MPSCNNNeuronTypePReLU, which require per-channel parameter values. For those kind of neuron activation functions, use appropriate setter functions. Default is descriptor with neuronType MPSCNNNeuronTypeNone.
    Note: in certain cases the neuron descriptor will be cached by the MPSNNGraph or the MPSCNNConvolution. If the neuron type changes after either is made, behavior is undefined.

Class MPSCNNConvolutionDescriptor

Nested Class Summary

Nested classes/interfaces inherited from class apple.NSObject

Constructor Summary

Method Summary

Methods inherited from class apple.NSObject

Methods inherited from class org.moe.natj.objc.ObjCObject

Methods inherited from class org.moe.natj.general.NativeObject

Methods inherited from class java.lang.Object

Constructor Detail

MPSCNNConvolutionDescriptor

Method Detail

accessInstanceVariablesDirectly

alloc

allocWithZone

automaticallyNotifiesObserversForKey

cancelPreviousPerformRequestsWithTarget

cancelPreviousPerformRequestsWithTargetSelectorObject

classFallbacksForKeyedArchiver

classForKeyedUnarchiver

cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannelsNeuronFilter

debugDescription_static

description_static

hash_static

instanceMethodForSelector

instanceMethodSignatureForSelector

instancesRespondToSelector

isSubclassOfClass

keyPathsForValuesAffectingValueForKey

new_objc

resolveClassMethod

resolveInstanceMethod

setVersion_static

superclass_static

version_static

copyWithZone

groups

init

inputFeatureChannels

kernelHeight

kernelWidth

neuron

outputFeatureChannels

setGroups

setInputFeatureChannels

setKernelHeight

setKernelWidth

setNeuron

setOutputFeatureChannels

setStrideInPixelsX

setStrideInPixelsY

strideInPixelsX

strideInPixelsY

cnnConvolutionDescriptorWithKernelWidthKernelHeightInputFeatureChannelsOutputFeatureChannels

dilationRateX

dilationRateY

encodeWithCoder

initWithCoder

neuronParameterA

neuronParameterB

neuronType

setBatchNormalizationParametersForInferenceWithMeanVarianceGammaBetaEpsilon

setDilationRateX

setDilationRateY

setNeuronToPReLUWithParametersA

setNeuronTypeParameterAParameterB

supportsSecureCoding

_supportsSecureCoding

fusedNeuronDescriptor

setFusedNeuronDescriptor